专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20130148513A1 CREATING PACKET TRAFFIC CLUSTERING MODELS FOR PROFILING PACKET FLOWS 审中-公开
标题翻译：创建分组流程的分组流量聚类模型
公开(公告)号：US20130148513A1
公开(公告)日：2013-06-13
申请号：US13315037
申请日：2011-12-08
申请人： Geza SZABO , Gergely PONGRÁCZ , Zoltán TURÁNYI
发明人： Geza SZABO , Gergely PONGRÁCZ , Zoltán TURÁNYI
IPC分类号： H04L12/26
CPC分类号： H04L41/142 , H04L41/16 , H04L43/028
摘要： Packet traffic profiling models are created based on packet headers of a packet flow at a first model aggregation level to obtain first flow information describing packet-oriented parameters of the flow. A machine learning algorithm (MLA) creates a first model based on the first information, determines if the first model achieves a first confidence level, and if not, defines multiple flow slices in the packet flow. Flow slices at a second higher model aggregation level are processed to obtain second flow information describing flow slice-oriented parameters of the packet flow, and an MLA creates a second model based on the second information to determine if the second model achieves a second confidence level. If so, the process completes; if not, further processing continues at a next level. One of the models is selected for profiling packet traffic flows.
摘要翻译：基于在第一模型聚合级别的分组流的分组报头创建分组业务分析模型，以获得描述该流的分组导向参数的第一流信息。机器学习算法（MLA）基于第一信息创建第一模型，确定第一模型是否实现第一置信水平，如果不是，则定义分组流中的多个流片。处理第二较高模型聚合级别的流片被处理以获得描述分组流的面向流片的参数的第二流信息，并且MLA基于第二信息创建第二模型以确定第二模型是否实现第二置信水平。如果是，则该过程完成; 如果没有，进一步的处理将继续下一个级别。选择其中一个模型来分析数据包流量。

2. 发明申请

US20120047200A1 USER BEHAVIOR BASED MOBILE BROADBAND USER PLANE TRAFFIC GENERATION SYSTEM AND METHOD FOR REAL-LIKE MEASUREMENT GENERATION 有权
标题翻译：基于用户行为的移动宽带用户平面生成系统和实时测量生成方法
公开(公告)号：US20120047200A1
公开(公告)日：2012-02-23
申请号：US12857684
申请日：2010-08-17
申请人： GEZA SZABO , GERGELY PONGRÁCZ , ZOLTÁN RICHÁRD TURÁNYI
发明人： GEZA SZABO , GERGELY PONGRÁCZ , ZOLTÁN RICHÁRD TURÁNYI
IPC分类号： G06F15/16 , G06F3/00
CPC分类号： H04L67/22 , H04L41/00 , H04L43/00
摘要： A system, a method, and a graphical user interface testing tool are described herein for constructing a validation trace (i.e., high-speed realistic network traffic) using a real network without causing privacy concerns. In one embodiment, the method comprises the steps of: (a) providing a client device which has one or more applications operating thereon and a graphical user interface; (b) recording user interactions on the client device; (c) extracting usage scenarios from real network traffic in the real network; (d) emulating user actions on the client device according to a specific user scenario by utilizing the recorded user interactions and the extracted usage scenarios to generate additional real traffic in the real network; and (e) creating the validation trace based on the generated additional real traffic and the extracted usage scenarios.
摘要翻译：本文描述了一种系统，方法和图形用户界面测试工具，用于使用真实网络构建验证跟踪（即，高速实际网络流量）而不引起隐私问题。在一个实施例中，该方法包括以下步骤：（a）提供在其上操作一个或多个应用的客户端设备和图形用户界面; （b）在客户端设备上记录用户交互; （c）从实际网络中的真实网络流量提取使用场景; （d）通过利用记录的用户交互和所提取的使用场景在实际网络中产生附加的实际业务，根据特定用户场景模拟客户端设备上的用户动作; 和（e）基于生成的附加实际流量和所提取的使用场景来创建验证跟踪。

3. 发明授权

US09124528B2 Method and arrangement for data clustering 有权
标题翻译：数据聚类的方法和布置
公开(公告)号：US09124528B2
公开(公告)日：2015-09-01
申请号：US13658031
申请日：2012-10-23
申请人： Geza Szabo , Gergely Pongrácz , Zoltán Richárd Turányi
发明人： Geza Szabo , Gergely Pongrácz , Zoltán Richárd Turányi
IPC分类号： H04L12/24 , H04L12/26 , H04L12/715 , H04L12/851
CPC分类号： H04L45/46 , H04L41/145 , H04L43/0882 , H04L43/16 , H04L47/2441
摘要： This disclosure relates a method within a network node and a corresponding network node for determining input information for creation of a data traffic clustering model. The method comprises obtaining data descriptors of data flows, wherein the data descriptors describe data of the data flows, and obtaining flow information of the data flows. In addition, the method comprises determining clustering model input information based on the obtained data descriptors and the obtained flow information. One exemplary advantage of the present disclosure is that it allows traffic clustering based solely on packet header information, making the present disclosure appropriate for handling encrypted traffic.
摘要翻译：本公开涉及网络节点和对应的网络节点中的方法，用于确定用于创建数据业务聚类模型的输入信息。该方法包括获取数据流的数据描述符，其中数据描述符描述数据流的数据，并获得数据流的流信息。另外，该方法包括基于所获得的数据描述符和获得的流信息来确定聚类模型输入信息。本公开的一个示例性优点是其仅允许基于分组报头信息的业务聚类，使得本公开适合于处理加密业务。

4. 发明申请

US20130100849A1 CREATING AND USING MULTIPLE PACKET TRAFFIC PROFILING MODELS TO PROFILE PACKET FLOWS 有权
标题翻译：创建和使用多个分组流量分析模型来分配分组流
公开(公告)号：US20130100849A1
公开(公告)日：2013-04-25
申请号：US13277735
申请日：2011-10-20
申请人： Geza SZABO , Gergely Pongrácz , Zoltan Turányi
发明人： Geza SZABO , Gergely Pongrácz , Zoltan Turányi
IPC分类号： H04L12/26
CPC分类号： G06K9/6292 , G06K9/6218 , G06K9/6267 , H04L47/2441
摘要： Hybrid packet traffic flow profiling technology inspects packet headers to classify packet traffic flows using clustering models developed using unsupervised learning based on known packet traffic flows and one or more traffic classification models developed using supervised learning based on the known packet traffic flows.
摘要翻译：混合分组业务流分析技术检查分组报头，使用基于已知分组业务流和使用基于已知分组业务流的监督学习开发的一个或多个业务分类模型的使用无监督学习开发的聚类模型对分组业务流进行分类。

5. 发明申请

US20150156102A1 A Method of and Network Server for Detecting Data Patterns in an Input Data Stream 有权
标题翻译：用于检测输入数据流中的数据模式的方法和网络服务器
公开(公告)号：US20150156102A1
公开(公告)日：2015-06-04
申请号：US14411547
申请日：2012-06-29
申请人： Geza Szabo , Wesley Davison Braga Melo , Gabor Sandor Enyedi , Stenio Fernandes , Gergely Pongrácz , Djamel Sadok
发明人： Geza Szabo , Wesley Davison Braga Melo , Gabor Sandor Enyedi , Stenio Fernandes , Gergely Pongrácz , Djamel Sadok
IPC分类号： H04L12/26
CPC分类号： H04L43/50 , H04L47/2483 , H04L63/1408
摘要： Computer controlled method, network server (42, 43, 44, 46, 48) and system (40) for detecting data patterns in a data stream (36) received by a computer (30). The data stream (36) comprising a plurality of data symbols. The computer (30) executes a finite automata (10) comprising a plurality of states (11, 12, 13, 14, 15) including a start state (11) and at least one accepting state (15). State transitions (16) are triggered by a data symbol (17a) according to a state transition register (17) and the method comprises the steps of determining (21), by the computer (30), from a data symbol register (18) whether a data symbol of the data stream (36) is comprised in a group of data symbols not resulting in an accepting state (15), and triggering (22), by the computer (30), a transition (16) to the start state (11) for data symbols comprised in the group and a transition (23) to a state (12, 13, 14, 15) according to the state transition register (17) for detecting the data pattern otherwise.
摘要翻译：计算机控制方法，用于检测由计算机（30）接收的数据流（36）中的数据模式的网络服务器（42,43,44,46,48）和系统（40）。数据流（36）包括多个数据符号。计算机（30）执行包括包括开始状态（11）和至少一个接受状态（15）的多个状态（11,12,13,14,15）的有限自动机（10）。状态转换（16）根据状态转移寄存器（17）由数据符号（17a）触发，并且该方法包括以下步骤：由计算机（30）从数据符号寄存器（18）确定（21）数据流（36）的数据符号是否包含在不导致接受状态（15）的数据符号组中，并且由计算机（30）触发（22）到开始的转换（16）状态（11），根据用于检测数据模式的状态转移寄存器（17）的转换（23）到状态（12,13,14,15）。

6. 发明授权

US08817655B2 Creating and using multiple packet traffic profiling models to profile packet flows 有权
标题翻译：创建和使用多个数据包流量分析模型来配置数据包流
公开(公告)号：US08817655B2
公开(公告)日：2014-08-26
申请号：US13277735
申请日：2011-10-20
申请人： Geza Szabo , Gergely Pongrácz , Zoltan Turányi
发明人： Geza Szabo , Gergely Pongrácz , Zoltan Turányi
IPC分类号： H04L12/26
CPC分类号： G06K9/6292 , G06K9/6218 , G06K9/6267 , H04L47/2441
摘要： Hybrid packet traffic flow profiling technology inspects packet headers to classify packet traffic flows using clustering models developed using unsupervised learning based on known packet traffic flows and one or more traffic classification models developed using supervised learning based on the known packet traffic flows.
摘要翻译：混合分组业务流分析技术检查分组报头，使用基于已知分组业务流和使用基于已知分组业务流的监督学习开发的一个或多个业务分类模型的使用无监督学习开发的聚类模型对分组业务流进行分类。

7. 发明授权

US08737204B2 Creating and using multiple packet traffic profiling models to profile packet flows 有权
标题翻译：创建和使用多个数据包流量分析模型来配置数据包流
公开(公告)号：US08737204B2
公开(公告)日：2014-05-27
申请号：US13098944
申请日：2011-05-02
申请人： Géza Szabó , Gergely Pongrácz , Djamel Sadok , Zoltán Richárd Turányi
发明人： Géza Szabó , Gergely Pongrácz , Djamel Sadok , Zoltán Richárd Turányi
IPC分类号： H04L12/26
CPC分类号： H04L43/026 , H04L41/145 , Y02D50/30
摘要： Multiple packet traffic profiling models are created from known packet traffic flows that are labeled, where a label is an actual value of a factor influencing one or more characteristics of the known packet traffic flow. Features, which are different from the factors, are measured for each flow. Flow clusters are defined from the labeled traffic flows by processing their features and labels. The profiling models are created based on cluster information. When an unknown packet flow is received, the multiple packet traffic profiling models are evaluated according to a confidence and a completeness associated with each of the packet traffic profiling models. The packet traffic profiling model with a predetermined confidence and completeness is selected and applied to profile the unknown packet traffic flow.
摘要翻译：已知标签的已知分组流量流创建多个分组业务分析模型，其中标签是影响已知分组业务流的一个或多个特征的因素的实际值。对于每个流量测量与因素不同的特征。通过处理其特征和标签，从标记的业务流定义流簇。分析模型基于集群信息创建。当接收到未知数据包流时，将根据与每个数据包流量分析模型相关联的置信度和完整性来评估多个数据包流量分析模型。选择并应用具有预定置信度和完整性的分组业务分析模型来对未知分组业务流进行简档分析。

8. 发明申请

US20130107715A1 METHOD AND ARRANGEMENT FOR DATA CLUSTERING 有权
标题翻译：数据聚类的方法和布置
公开(公告)号：US20130107715A1
公开(公告)日：2013-05-02
申请号：US13658031
申请日：2012-10-23
申请人： Geza Szabo , Gergely Pongrácz , Zoltán Richárd Turányi
发明人： Geza Szabo , Gergely Pongrácz , Zoltán Richárd Turányi
IPC分类号： H04L12/56
CPC分类号： H04L45/46 , H04L41/145 , H04L43/0882 , H04L43/16 , H04L47/2441
摘要： This disclosure relates a method within a network node and a corresponding network node for determining input information for creation of a data traffic clustering model. The method comprises obtaining data descriptors of data flows, wherein the data descriptors describe data of the data flows, and obtaining flow information of the data flows. In addition, the method comprises determining clustering model input information based on the obtained data descriptors and the obtained flow information. One exemplary advantage of the present disclosure is that it allows traffic clustering based solely on packet header information, making the present disclosure appropriate for handling encrypted traffic.
摘要翻译：本公开涉及网络节点和对应的网络节点中的方法，用于确定用于创建数据业务聚类模型的输入信息。该方法包括获取数据流的数据描述符，其中数据描述符描述数据流的数据，并获得数据流的流信息。另外，该方法包括基于所获得的数据描述符和获得的流信息来确定聚类模型输入信息。本公开的一个示例性优点是其仅允许基于分组报头信息的业务聚类，使得本公开适合于处理加密业务。

9. 发明授权

US09825841B2 Method of and network server for detecting data patterns in an input data stream 有权
公开(公告)号：US09825841B2
公开(公告)日：2017-11-21
申请号：US14411547
申请日：2012-06-29
申请人： Geza Szabo , Wesley Davison Braga Melo , Gabor Sandor Enyedi , Stenio Fernandes , Gergely Pongrácz , Djamel Sadok
发明人： Geza Szabo , Wesley Davison Braga Melo , Gabor Sandor Enyedi , Stenio Fernandes , Gergely Pongrácz , Djamel Sadok
IPC分类号： G06F15/16 , H04L12/26 , H04L12/851 , H04L29/06
CPC分类号： H04L43/50 , H04L47/2483 , H04L63/1408
摘要： Computer controlled method, network server (42, 43, 44, 46, 48) and system (40) for detecting data patterns in a data stream (36) received by a computer (30). The data stream (36) comprising a plurality of data symbols. The computer (30) executes a finite automata (10) comprising a plurality of states (11, 12, 13, 14, 15) including a start state (11) and at least one accepting state (15). State transitions (16) are triggered by a data symbol (17a) according to a state transition register (17) and the method comprises the steps of determining (21), by the computer (30), from a data symbol register (18) whether a data symbol of the data stream (36) is comprised in a group of data symbols not resulting in an accepting state (15), and triggering (22), by the computer (30), a transition (16) to the start state (11) for data symbols comprised in the group and a transition (23) to a state (12, 13, 14, 15) according to the state transition register (17) for detecting the data pattern otherwise.

10. 发明申请

US20120281590A1 CREATING AND USING MULTIPLE PACKET TRAFFIC PROFILING MODELS TO PROFILE PACKET FLOWS 有权
标题翻译：创建和使用多个分组流量分析模型来分配分组流
公开(公告)号：US20120281590A1
公开(公告)日：2012-11-08
申请号：US13098944
申请日：2011-05-02
申请人： Géza SZABÓ , Gergely Pongrácz , Djamel Sadok , Zoltán Richárd Turányi
发明人： Géza SZABÓ , Gergely Pongrácz , Djamel Sadok , Zoltán Richárd Turányi
IPC分类号： H04L12/26
CPC分类号： H04L43/026 , H04L41/145 , Y02D50/30
摘要： Multiple packet traffic profiling models are created from known packet traffic flows that are labeled, where a label is an actual value of a factor influencing one or more characteristics of the known packet traffic flow. Features, which are different from the factors, are measured for each flow. Flow clusters are defined from the labeled traffic flows by processing their features and labels. The profiling models are created based on cluster information. When an unknown packet flow is received, the multiple packet traffic profiling models are evaluated according to a confidence and a completeness associated with each of the packet traffic profiling models. The packet traffic profiling model with a predetermined confidence and completeness is selected and applied to profile the unknown packet traffic flow.
摘要翻译：已知标签的已知分组流量流创建多个分组业务分析模型，其中标签是影响已知分组业务流的一个或多个特征的因素的实际值。对于每个流量测量与因素不同的特征。通过处理其特征和标签，从标记的业务流定义流簇。分析模型基于集群信息创建。当接收到未知数据包流时，将根据与每个数据包流量分析模型相关联的置信度和完整性来评估多个数据包流量分析模型。选择并应用具有预定置信度和完整性的分组业务分析模型来对未知分组业务流进行简档分析。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式